How Does OCR Work?

by Wanda Brito

What is OCR?

Optical character recognition, more commonly known as OCR, is the interpretation of scanned images of handwritten, typed or printed text into text that can be edited on a computer. There are various components that work together to perform optical character recognition. These elements include pattern identification, artificial intelligence and machine vision. Research in this area continues, developing more effective read rates and greater precision. The two main systems used to perform OCR are "matrix matching" and "feature extraction." Matrix matching is the simpler and the more common, as well as the more limited, of the two.

Matrix Matching

Matrix matching (also known as pattern matching) associates what the scanner perceives as a character with a stored collection of bitmapped patterns or outlines of characters. When an image corresponds to one of these selected bitmaps within a certain degree of likeness, the program identifies that image as the equivalent plain text character. An evident shortcoming of this system is that it can only be used for the fonts and sizes in its repertoire.

Feature Extraction

Feature extraction is also known as intelligent character recognition (ICR), or topological feature analysis. It is a kind of optical character recognition that does not rely on precise matching to set templates. The program searches for common elements such as open spaces, closed forms, lines - diagonals intersecting and so on.

About the Author

Wanda Brito was born to write. She has written professionally since 1998 - developing surveys, presentations and marketing research reports — and has been writing and proofreading freelance since 2007. Her work has been featured on She holds a Bachelor of Arts in Spanish literature from Colgate University and a Master of Science in administration from Metropolitan College of New York.